---
title: "Self-Guide:一种基于自我规划的大语言模型推理增强方法 — 刘艺彬 2025"
description: "Chain-of-thought prompting asks a large language model to plan a solution and execute it in a single pass."
authors: ["刘艺彬", "刘正皓", "闫宇坤", "于是", "王硕", "杨麟儿", "陈慧敏", "谷峪", "于戈"]
year: 2025
venue: "中文信息学报 (Journal of Chinese Information Processing)"
source: "http://jcip.cipsc.org.cn/article/id/zwxxxb_3896"
licence: "Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2025-self-guide-enhancing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2025-self-guide-enhancing/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / Self-Guide:一种基于自我规划的大语言模型推理增强方法

# Self-Guide:一种基于自我规划的大语言模型推理增强方法

**Authors:** 刘艺彬, 刘正皓, 闫宇坤, 于是, 王硕, 杨麟儿, 陈慧敏, 谷峪, 于戈 · **Year:** 2025 · **Venue:** 中文信息学报 (Journal of Chinese Information Processing) · **Licence:** Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报

**Links:** [Publisher's page](http://jcip.cipsc.org.cn/article/id/zwxxxb_3896) · [PDF](http://jcip.cipsc.org.cn/cn/article/pdf/preview/zwxxxb_3896.pdf)

## Summary
Chain-of-thought prompting asks a large language model to plan a solution and execute it in a single pass. Drawing on Sweller's Cognitive Load Theory, the authors argue that this double burden can overload the model and produce hallucinated or unproductive reasoning. Their method, Self-Guide, splits planning from answering and needs no fine-tuning or external tools. In a zero-shot setting, the model first writes a "Guideline" for the question, covering relevant background knowledge, an interpretation of the question, and a step-by-step plan. In parallel, it produces an ordinary Zero-Shot-CoT answer. A template then asks the model to revisit that answer in light of the Guideline, fixing errors and refining the final response. The approach was tested with GPT-3.5-turbo-1106 on four kinds of reasoning, where it beat Zero-Shot and CoT baselines. Guidelines produced by GPT-3.5 also gave large gains to the weaker LLaMA2 chat models. This suggests a stronger model's plans can be handed to a smaller one, a cheap route to better reasoning without any training.

## Key points
- **Benchmarks:**
  - MMLU (knowledge understanding, 500 random samples)
  - StrategyQA (multi-hop QA, full set)
  - Date Understanding from BIG-bench (temporal reasoning, full set)
  - CLUTRR (kinship reasoning, 500 random samples)
- **Gains:** on GPT-3.5-turbo-1106, the average improvement over standard chain-of-thought was about 2%.
- **Transfer to smaller models:** Guidelines from GPT-3.5 lifted LLaMA2-7B-Chat and LLaMA2-13B-Chat by over 10%.
- **Evaluation and decoding:**
  - Metric: accuracy via lowercase exact string matching, with task-specific answer extraction (e.g., MM/DD/YYYY date patterns for Date).
  - Decoding temperature: 0.2.
- **Availability:** code and data are released at github.com/NEUIR/Self-Guide (Northeastern University, with Tsinghua University and Beijing Language and Culture University co-authors).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@article{2025self,
  title = {{Self-Guide:一种基于自我规划的大语言模型推理增强方法}},
  author = {刘艺彬 and 刘正皓 and 闫宇坤 and 于是 and 王硕 and 杨麟儿 and 陈慧敏 and 谷峪 and 于戈},
  journal = {中文信息学报 (Journal of Chinese Information Processing)},
  year = {2025},
  url = {http://jcip.cipsc.org.cn/article/id/zwxxxb_3896}
}
```

- [← previous Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/)
- [next → Semantics drives analogical change in Germanic strong verb paradigms: a phylogenetic study](https://md.research.elamur.ai/free/en/papers/craevschi-2025-semantics-drives-analogical-change-germanic/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)